Zagazig University Digital Repository
Home
Thesis & Publications
All Contents
Publications
Thesis
Graduation Projects
Research Area
Research Area Reports
Search by Research Area
Universities Thesis
ACADEMIC Links
ACADEMIC RESEARCH
Zagazig University Authors
Africa Research Statistics
Google Scholar
Research Gate
Researcher ID
CrossRef
A novel method for detection of tuberculosis in chest radiographs using artificial ecosystem-based optimisation of deep neural network features
Faculty
Science
Year:
2020
Type of Publication:
ZU Hosted
Pages:
Authors:
Mohamed El Sayed Ahmed Muhamed
Staff Zu Site
Abstract In Staff Site
Journal:
Symmetry MDPI
Volume:
Keywords :
, novel method , detection , tuberculosis , chest radiographs
Abstract:
Tuberculosis (TB) is is an infectious disease that generally attacks the lungs and causes death for millions of people annually. Chest radiography and deep-learning-based image segmentation techniques can be utilized for TB diagnostics. Convolutional Neural Networks (CNNs) has shown advantages in medical image recognition applications as powerful models to extract informative features from images. Here, we present a novel hybrid method for efficient classification of chest X-ray images. First, the features are extracted from chest X-ray images using MobileNet, a CNN model, which was previously trained on the ImageNet dataset. Then, to determine which of these features are the most relevant, we apply the Artificial Ecosystem-based Optimization (AEO) algorithm as a feature selector. The proposed method is applied to two public benchmark datasets (Shenzhen and Dataset 2) and allows them to achieve high performance and reduced computational time. It selected successfully only the best 25 and 19 (for Shenzhen and Dataset 2, respectively) features out of about 50,000 features extracted with MobileNet, while improving the classification accuracy (90.2% for Shenzen dataset and 94.1% for Dataset 2). The proposed approach outperforms other deep learning methods, while the results are the best compared to other recently published works on both datasets. View Full-Text
Author Related Publications
Mohamed El Sayed Ahmed Muhamed, "A Grunwald–Letnikov based Manta ray foraging optimizer for global optimization and image segmentation", Elsevier, 2020
More
Mohamed El Sayed Ahmed Muhamed, "A novel hybrid gradient-based optimizer and grey wolf optimizer feature selection method for human activity recognition using smartphone sensors", MDPI, 2021
More
Mohamed El Sayed Ahmed Muhamed, "Efficient schemes for playout latency reduction in P2P-VOD systems", Springer, 2018
More
Mohamed El Sayed Ahmed Muhamed, "a novel algorithm for source localization based on nonnegative matrix factroization using \alpha 'beta divergence in chochleagram", WSEAS, 2013
More
Mohamed El Sayed Ahmed Muhamed, "Open cluster membership probability based on K-means clustering algorithm", Springer, 2016
More
Department Related Publications
Rodyna Ahmed Mahmoud, "Pre-Open Sets with Ideal", Scientific Research Platform (SRP), 2013
More
Rodyna Ahmed Mahmoud, "ON BCL-ALGEBRA", Council for Innovative Research, 2013
More
Yasser AbdelAziz Amer Tolba, "The improved (G’/G) - expansion method for constructing exact traveling wave solutions for a nonlinear PDE of nanobiosciences", USA, 2013
More
Alaa Hassan Attia Hassan, "A Unified Representation of Some Starlike and Convex Harmonic Functions with Negative Coefficients", AGH University of Science and Technology Press, Krakow 2013, Poland, 2013
More
Alaa Hassan Attia Hassan, "Generalizations of Hadamard Procuct of Certain Meromorphic Multivalent Functions with Positive Coefficients", Istanbul Universitesi, Turkey, 2013
More
جامعة المنصورة
جامعة الاسكندرية
جامعة القاهرة
جامعة سوهاج
جامعة الفيوم
جامعة بنها
جامعة دمياط
جامعة بورسعيد
جامعة حلوان
جامعة السويس
شراقوة
جامعة المنيا
جامعة دمنهور
جامعة المنوفية
جامعة أسوان
جامعة جنوب الوادى
جامعة قناة السويس
جامعة عين شمس
جامعة أسيوط
جامعة كفر الشيخ
جامعة السادات
جامعة طنطا
جامعة بنى سويف